Penilaian Estetika Foto Makanan Berdasarkan Atribut Visual: Komposisi, Tekstur, Dan Kompleksitas Warna

Noveri, Ferza (2025) Penilaian Estetika Foto Makanan Berdasarkan Atribut Visual: Komposisi, Tekstur, Dan Kompleksitas Warna. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5025211097-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (7MB) | Request a copy

Abstract

Di era digital ini, visualisasi makanan memiliki peran penting dalam menarik minat konsumen, khususnya di platform e-commerce dan media sosial. Bagi pelaku Usaha Mikro, Kecil, dan Menengah (UMKM) di bidang kuliner, kualitas tampilan foto makanan sangat berpengaruh terhadap daya tarik dan citra produk. Namun, keterbatasan anggaran sering kali menjadi hambatan bagi UMKM untuk menggunakan jasa fotografer profesional. Akibatnya, banyak foto produk memiliki kualitas visual yang kurang optimal dan tidak mampu memaksimalkan minat pembeli. Oleh karena itu, penelitian ini mengusulkan pemanfaatan teknologi Artificial Intelligence (AI) untuk membantu UMKM dalam menilai kualitas estetika foto makanan secara otomatis. Dengan adanya sistem penilaian visual berbasis AI yang objektif dan andal, pelaku usaha dapat memperoleh umpan balik terhadap kualitas foto produk mereka serta meningkatkan daya tarik visual tanpa memerlukan biaya tambahan yang besar. Penelitian ini melakukan ekstraksi fitur komposisi, tekstur, dan warna pada gambar. Eksperimen dilakukan menggunakan dataset public Gourmet Photography Datase (GPD) yang terdiri dari 24.000 foto makanan. Model klasifikasi yang digunakan adalah SVM, Random Forest, MLP, VGG16+MLP, dan VGG19+MLP. Hasil penelitian dievaluasi menggunakan metrik evaluasi seperti accuracy, precision, recall, dan F1-Score untuk setiap model klasifikasi yang digunakan. Di antara keempat model klasifikasi yang digunakan, model VGG16+MLP memiliki kinerja terbaik dengan accuracy sebesar 0,9166, precision sebesar 0,9186, recall sebesar 0,9298, dan F1-Score sebesar 0,9241.
======================================================================================================================================
In this digital era, food visualization plays an important role in attracting consumer interest, especially on e-commerce platforms and social media. For Micro, Small, and Medium Enterprises (MSMEs) in the culinary sector, the quality of food photography greatly influences the appeal and image of the product. However, budget constraints are often an obstacle for MSMEs to use the services of professional photographers. As a result, many product photos have less than optimal visual quality and are unable to maximize buyer interest. Therefore, this study proposes the use of Artificial Intelligence (AI) technology to help MSMEs in automatically assessing the aesthetic quality of food photos. With an objective and reliable AI-based visual assessment system, business actors can get feedback on the quality of their product photos and improve visual appeal without requiring large additional costs. This study extracts composition, texture, and color features from images. The experiment was conducted using the public Gourmet Photography Datase (GPD) dataset consisting of 24,000 food photos. The classification models used were SVM, Random Forest, MLP, VGG16 + MLP, and VGG19 + MLP. The results of the study were evaluated using evaluation metrics such as accuracy, precision, recall, and F1-Score for each classification model used. Among the four classification models used, the VGG16+MLP model has the best performance with an accuracy of 0.9166, a precision of 0.9186, a recall of 0.9298, and an F1-Score of 0.9241.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Classification, Composition, Color, Texture, Food Photos, Aesthetic. Klasifikasi, Komposisi, Warna, Tekstur, Foto Makanan, Estetika.
Subjects:	T Technology > T Technology (General) > T57.5 Data Processing
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Ferza Noveri
Date Deposited:	31 Jul 2025 01:26
Last Modified:	31 Jul 2025 01:26
URI:	http://repository.its.ac.id/id/eprint/123224

Actions (login required)

View Item